Accurately modeling and understanding player experience is crucial for designing engaging puzzle games. A common approach to achieve this involves collecting diverse user data to train predictive playtesting models that mimic player behavior. However, existing data-driven methods often lack the ability to capture the full range of player strategies and require extensive feature engineering and network architecture modeling. This limitation becomes particularly evident when new game mechanics or features are introduced, necessitating continual adjustments to the models.
To address these challenges, we propose a more generalized representation that reduces - or even eliminates - the need for ongoing feature-engineering maintenance. Specifically, we investigate two general-purpose network architectures: (a) a transformer-based model (BERT) and (b) a graph attention model (GAT), both designed to effectively capture the relational structure of Candy Crush Saga (CCS) game boards. Our experiments compare these approaches to Convolutional Neural Networks (CNN) baselines, revealing better performance on challenging board configurations and underscoring the benefits of our generalizable representation.
Blogger's Review: This article delves into the critical choice of models in game testing, revealing that GAT and BERT demonstrate greater adaptability in capturing player behaviors, especially when new features are introduced. This offers game designers fresh insights on leveraging advanced deep learning architectures to enhance player experiences. It is hoped that more research in this area will propel the field forward.